To explore the vulnerability of deep neural networks (DNNs), many attack
paradigms have been well studied, such as the poisoning-based backdoor attack
in the training stage and the adversarial attack in the inference stage. In
this paper, we study a novel attack paradigm, which modifies model parameters
in the deployment stage for malicious purposes. Specifically, our goal is to
misclassify a specific sample into a target class without any sample
modification, while not significantly reduce the prediction accuracy of other
samples to ensure the stealthiness. To this end, we formulate this problem as a
binary integer programming (BIP), since the parameters are stored as binary
bits ($i.e.$, 0 and 1) in the memory. By utilizing the latest technique in
integer programming, we equivalently reformulate this BIP problem as a
continuous optimization problem, which can be effectively and efficiently
solved using the alternating direction method of multipliers (ADMM) method.
Consequently, the flipped critical bits can be easily determined through
optimization, rather than using a heuristic strategy. Extensive experiments
demonstrate the superiority of our method in attacking DNNs.

Go to Source of this post
Author Of this post: <a href="http://arxiv.org/find/cs/1/au:+Bai_J/0/1/0/all/0/1">Jiawang Bai</a>, <a href="http://arxiv.org/find/cs/1/au:+Wu_B/0/1/0/all/0/1">Baoyuan Wu</a>, <a href="http://arxiv.org/find/cs/1/au:+Zhang_Y/0/1/0/all/0/1">Yong Zhang</a>, <a href="http://arxiv.org/find/cs/1/au:+Li_Y/0/1/0/all/0/1">Yiming Li</a>, <a href="http://arxiv.org/find/cs/1/au:+Li_Z/0/1/0/all/0/1">Zhifeng Li</a>, <a href="http://arxiv.org/find/cs/1/au:+Xia_S/0/1/0/all/0/1">Shu-Tao Xia</a>

By admin